Topic
Phrase
About: Phrase is a research topic. Over the lifetime, 12580 publications have been published within this topic receiving 317823 citations. The topic is also known as: syntagma & phrases.
Papers published on a yearly basis
Papers
More filters
••
19 Jun 2008TL;DR: The experiments of the UC Berkeley team on improving English-Spanish machine translation of news text, as part of the WMT'08 Shared Translation Task, describe the experiments and experiment with domain adaptation, building two separate phrase translation models and two separate language models.
Abstract: We describe the experiments of the UC Berkeley team on improving English-Spanish machine translation of news text, as part of the WMT'08 Shared Translation Task. We experiment with domain adaptation, combining a small in-domain news bi-text and a large out-of-domain one from the Europarl corpus, building two separate phrase translation models and two separate language models. We further add a third phrase translation model trained on a version of the news bi-text augmented with monolingual sentence-level syntactic paraphrases on the source-language side, and we combine all models in a log-linear model using minimum error rate training. Finally, we experiment with different tokenization and recasing rules, achieving 35.09% Bleu score on the WMT'07 news test data when translating from English to Spanish, which is a sizable improvement over the highest Bleu score achieved on that dataset at WMT'07: 33.10% (in fact, by our system). On the WMT'08 English to Spanish news translation, we achieve 21.92%, which makes our team the second best on Bleu score.
73 citations
••
TL;DR: Analysis of the patients' performance indicated that patients had difficulty producing both grammatical forms and thematic roles, and patients showed differential difficulty on sentence types that had more grammatical elements and in which the order of thematic role was non-canonical.
73 citations
••
06 Oct 2005TL;DR: It is found that Chinese-English word alignment performance is comparable to that of IBM Model-4 even over large training bitexts.
Abstract: HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that alignment and parameter estimation can be performed efficiently. We find that Chinese-English word alignment performance is comparable to that of IBM Model-4 even over large training bitexts. Phrase pairs extracted from word alignments generated under the model can also be used for phrase-based translation, and in Chinese to English and Arabic to English translation, performance is comparable to systems based on Model-4 alignments. Direct phrase pair induction under the model is described and shown to improve translation performance.
73 citations
••
IBM1
TL;DR: This paper introduces a sentence-level or batch-level vocabulary, which is only a very small sub-set of the full output vocabulary for each sentence or batch, which reduces both the computing time and the memory usage of neural machine translation models.
Abstract: In order to capture rich language phenomena, neural machine translation models have to use a large vocabulary size, which requires high computing time and large memory usage. In this paper, we alleviate this issue by introducing a sentence-level or batch-level vocabulary, which is only a very small sub-set of the full output vocabulary. For each sentence or batch, we only predict the target words in its sentencelevel or batch-level vocabulary. Thus, we reduce both the computing time and the memory usage. Our method simply takes into account the translation options of each word or phrase in the source sentence, and picks a very small target vocabulary for each sentence based on a wordto-word translation model or a bilingual phrase library learned from a traditional machine translation model. Experimental results on the large-scale English-toFrench task show that our method achieves better translation performance by 1 BLEU point over the large vocabulary neural machine translation system of Jean et al. (2015).
73 citations
••
TL;DR: A new developmental hypothesis is concluded: development in question formation occurs in integrating language-specific knowledge related to inflection with the principles of Universal Grammar which allow grammatical inversion.
Abstract: This paper examines two- to five-year-old children's knowledge of inversion in English yes/no questions through a new experimental study. It challenges the view that the syntax for inversion develops slowly in child English and tests the hypothesis that grammatical competence for inversion is present from the earliest testable ages of the child's sentence production. The experimental design is based on the premise that a valid test of this hypothesis must dissociate from inversion various language-specific aspects of English grammar, including its inflectional system. An elicited imitation method was used to test parallel, lexically-matched declarative and question structures across several different verb types in a design which dissociated subject-auxiliary inversion from the English-specific realization of the inflectional/auxiliary system. Using this design, the results showed no significant difference in amount or type of children's errors between declarative (non-inverted) and question (inverted) sentences with modals or auxiliary be, but a significant difference for sentences with main verbs (requiring reconstruction of inflection through do-support) and copula be. The results from sentences with auxiliary be and those with modals indicate that knowledge of inversion is present throughout our very young sample and does not develop during this time. We argue that these results indicate that the grammar of inversion is present from the youngest ages tested. Our results also provide evidence of development relevant to the English-specific inflectional system. We conclude with a new developmental hypothesis: development in question formation occurs in integrating language-specific knowledge related to inflection with the principles of Universal Grammar which allow grammatical inversion.
72 citations